Paper Citation Record · LEDGER

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens

As of 21 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2607.26350.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.26350 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T00:08:00.302195Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T00:07:54.620862Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

41 of 41 outbound references displayed

verified exact0
verified fuzzy0
unresolved39
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fefd3f96-61bc-463c-910b-6f7750066bb9 · outbound

This paper cites an unresolved cited work.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:54.507488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb3db4b6-a994-48be-80c2-7a75965a72fd · outbound

This paper cites Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:54.620862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33331adb-dd85-4fbf-b055-7f9ddb8ca43c · outbound

This paper cites Experimental Design The experiments are designed to decouple language sensitiv- ity in codec-based SSL across the NAC and the SSL pre- training stage (Fig.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Experimental Design The experiments are designed to decouple language sensitiv- ity in codec-based SSL across the NAC and the SSL pre- training stage (Fig

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:54.762971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ee3d976-48f4-4e09-adc0-f46b77ddf50b · outbound

This paper cites Comparison across NACs To answer RQ1, we examined language sensitivity on NAC- reconstructed waveforms using the setup in Section 3.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Comparison across NACs To answer RQ1, we examined language sensitivity on NAC- reconstructed waveforms using the setup in Section 3

Reference 4

Resolution: malformed identifier; no resolver link, observed 2026-08-01T00:07:54.860169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7e649af-3eee-4fd8-8246-8ab180a74159 · outbound

This paper cites Experimental Setup We now analyze the language sensitivity within codec-based SSLs to answer RQ2 and RQ3.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Experimental Setup We now analyze the language sensitivity within codec-based SSLs to answer RQ2 and RQ3

Reference 5

Resolution: malformed identifier; no resolver link, observed 2026-08-01T00:07:55.020198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f71cac89-cabe-4cb3-89fa-7a8bcdb0fd0d · outbound

This paper cites an unresolved cited work.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:55.186719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cb6a1f5-e635-434d-99b0-086182f22111 · outbound

This paper cites This study is also supported by AIST policy-based bud- get project ’R&D on Generative AI Foundation Models for the Physical Domain’.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens This study is also supported by AIST policy-based bud- get project ’R&D on Generative AI Foundation Models for the Physical Domain’

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:55.352502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 654c1652-bb83-4fd0-8f40-d23bed737b20 · outbound

This paper cites The authors reviewed and edited the out- put as needed and take full responsibility for the content of the manuscript.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens The authors reviewed and edited the out- put as needed and take full responsibility for the content of the manuscript

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:55.518867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 116b993c-19a8-4929-aea9-3a6ab0d76741 · outbound

This paper cites Self-supervised speech representation learning: A review,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Self-supervised speech representation learning: A review,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:55.625354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ed1b349-ae89-427d-af2a-83680ffe99a1 · outbound

This paper cites wav2vec 2.0: A framework for self-supervised learning of speech representa- tions,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens wav2vec 2.0: A framework for self-supervised learning of speech representa- tions,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:55.847196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfc751a2-5be8-47e8-88b5-15cad692abb7 · outbound

This paper cites HuBERT: Self-supervised speech representation learning by masked prediction of hidden units,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens HuBERT: Self-supervised speech representation learning by masked prediction of hidden units,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:56.064595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20ff284d-9fef-4890-a716-69a8cdf30068 · outbound

This paper cites Reducing barriers to self-supervised learning: HuBERT pre- training with academic compute,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Reducing barriers to self-supervised learning: HuBERT pre- training with academic compute,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:56.226999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c654289-a547-4374-b8a4-5c0faf2ba60e · outbound

This paper cites Fast- HuBERT: An efficient training framework for self-supervised speech representation learning,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Fast- HuBERT: An efficient training framework for self-supervised speech representation learning,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:56.392868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 620ad765-d904-44c2-9b68-cb330072536d · outbound

This paper cites Towards efficient self-supervised repre- sentation learning in speech processing,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Towards efficient self-supervised repre- sentation learning in speech processing,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:56.519582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc64806-f355-4762-91e5-a04a7e306ac9 · outbound

This paper cites Efficient training of self-supervised speech foundation models on a com- pute budget,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Efficient training of self-supervised speech foundation models on a com- pute budget,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:56.665696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16408a39-76be-4957-8ca3-9a824474e5ca · outbound

This paper cites ESPnet-Codec: Comprehensive training and eval- uation of neural codecs for audio, music, and speech,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens ESPnet-Codec: Comprehensive training and eval- uation of neural codecs for audio, music, and speech,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:56.869304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 824c96ac-360a-4039-b480-a6302559ecf8 · outbound

This paper cites Codec2Vec: Self-supervised speech representation learning using neural speech codecs,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Codec2Vec: Self-supervised speech representation learning using neural speech codecs,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:57.054584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53fbc980-ea4b-4bee-bdd9-0dbe2918c7ca · outbound

This paper cites Discrete audio tokens: More than a survey!.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Discrete audio tokens: More than a survey!

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:57.223360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca62793e-fc67-4180-9204-8d1fd72d8f4a · outbound

This paper cites Exploration of language dependency for Japanese self-supervised speech rep- resentation models,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Exploration of language dependency for Japanese self-supervised speech rep- resentation models,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:57.385923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20041a20-15a1-4834-bbf5-5f7627ca08bc · outbound

This paper cites Evaluating self- supervised speech models on a Taiwanese Hokkien corpus,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Evaluating self- supervised speech models on a Taiwanese Hokkien corpus,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:57.394568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 123dbe17-1647-43f9-b7ba-2018ec1e0df5 · outbound

This paper cites How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenario.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenario

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:57.438397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aa9b57f-c5ea-464c-b6fd-bb8a15dbfbd2 · outbound

This paper cites On the language and gen- der biases in PSTN, V oIP and neural audio codecs,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens On the language and gen- der biases in PSTN, V oIP and neural audio codecs,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:57.551072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75521c40-7764-40ad-bac1-ede9ac8d62af · outbound

This paper cites Do neural codecs generalize? A controlled study across unseen languages and non-speech tasks,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Do neural codecs generalize? A controlled study across unseen languages and non-speech tasks,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:57.641516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 899c98ec-650b-486b-86dc-e2b13b1ffb3c · outbound

This paper cites High-fidelity audio compression with improved RVQGAN,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens High-fidelity audio compression with improved RVQGAN,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:57.751129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78fe2f8c-8ccd-4a78-95bd-55cb252a4fd8 · outbound

This paper cites Libri-Light: A benchmark for ASR with limited or no supervi- sion,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Libri-Light: A benchmark for ASR with limited or no supervi- sion,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:57.879132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff02645c-fa42-47db-bc6b-985f522ad149 · outbound

This paper cites Construction of a large-scale Japanese ASR corpus on TV recordings,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Construction of a large-scale Japanese ASR corpus on TV recordings,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:58.012150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d64d086b-2a8b-4181-a2f9-a7806a94e7a9 · outbound

This paper cites WenetSpeech: A 10000+ hours multi-domain Mandarin corpus for speech recognition,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens WenetSpeech: A 10000+ hours multi-domain Mandarin corpus for speech recognition,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:58.137496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcc94430-e5e7-4e6c-9722-0bae2b72b9eb · outbound

This paper cites AISHELL-1: An open-source Mandarin speech corpus and a speech recognition baseline,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens AISHELL-1: An open-source Mandarin speech corpus and a speech recognition baseline,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:58.313953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ab7c911-91d5-4b9d-bd27-dc836da2e61a · outbound

This paper cites Lib- riSpeech: An ASR corpus based on public domain audio books,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Lib- riSpeech: An ASR corpus based on public domain audio books,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:58.465638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc2a30f2-c2ba-40d4-8404-0e896ace18aa · outbound

This paper cites Corpus of spontaneous Japanese: Its design and evaluation,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Corpus of spontaneous Japanese: Its design and evaluation,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:58.628318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 432b14b2-abcc-4377-ad85-ffcc13358107 · outbound

This paper cites Cor- pus of Japanese dialects (COJADS),.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Cor- pus of Japanese dialects (COJADS),

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:58.798813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 811a1fee-a857-49c3-bff6-edc2c4593b22 · outbound

This paper cites IEMOCAP: Interactive emotional dyadic motion capture database,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens IEMOCAP: Interactive emotional dyadic motion capture database,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:58.954773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c9d8b01-6992-49f1-9d37-5c711f8398e8 · outbound

This paper cites Construction and anal- ysis of phonetically and prosodically balanced emotional speech database,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Construction and anal- ysis of phonetically and prosodically balanced emotional speech database,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:59.087574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d97eaa6b-fd42-4689-aa42-08d964e68376 · outbound

This paper cites EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:59.254037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 343991d8-db76-4fd9-837e-6844cfdbc008 · outbound

This paper cites ESPnet: End-to-end speech processing toolkit,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens ESPnet: End-to-end speech processing toolkit,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:59.394060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5414aac1-0c07-4715-983f-32b2ecd520f1 · outbound

This paper cites SUPERB: Speech processing universal performance benchmark,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens SUPERB: Speech processing universal performance benchmark,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:59.519709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b4d489e-88e2-4808-99a7-308fd40b85d7 · outbound

This paper cites High fidelity neural audio compression,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens High fidelity neural audio compression,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:59.710658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f50c16f-5142-4df0-8c02-cfa3ae832091 · outbound

This paper cites SpeechTok- enizer: Unified speech tokenizer for speech language models,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens SpeechTok- enizer: Unified speech tokenizer for speech language models,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:59.839603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49ad40c1-7a5b-4958-8dec-b39d0d4ef851 · outbound

This paper cites Codec does matter: Ex- ploring the semantic shortcoming of codec for audio language model,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens Codec does matter: Ex- ploring the semantic shortcoming of codec for audio language model,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T00:07:59.998830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dc59031-9f1d-4b0c-865a-2881df3972ea · outbound

This paper cites PAST: Phonetic-acoustic speech tokenizer,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens PAST: Phonetic-acoustic speech tokenizer,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T00:08:00.125419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c2d0a7c-e5c6-4540-8c54-4dcb1f8b53cf · outbound

This paper cites fairseq: A fast, extensible toolkit for sequence modeling,.

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens fairseq: A fast, extensible toolkit for sequence modeling,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T00:08:00.302195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation eb3db4b6-a994-48be-80c2-7a75965a72fd · inbound